Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A Roslyn-based MCP server that gives AI agents deep semantic understanding of .NET codebases — type hierarchies, call graphs, DI registrations, diagnostics, refactoring, and more.
Enable Claude Code to call Codex (GPT-5) asynchronously, filtering out thinking processes to save 95% context tokens.
CROW - Your AI Agent. MCPs, OpenRouter, Any Model or local. It's your choice.
A web-based control panel designed to simplify the management of MCP-to-OpenAPI (mcpo) instances and their server configurations. It provides a user-friendly UI and an API for interacting with mcpo.
Observal is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.
A Model-Context Protocol server for the MITRE ATT&CK knowledge base
A minimal MCP server built on crawl4ai for LLM-friendly web extraction
An MCP server that exposes the Revit API docs and sample code to LLMs.
Safe DOCX suite: docx-primitives, docx-comparison, safe-docx MCP server
AI-powered CLI and MCP server for browsing GitHub project documentation (unofficial tool)
AI-powered X.com automation using Claude Agent SDK and Chrome DevTools MCP
gives AI agents a persistent, searchable memory they can use across sessions. V2.1 adds SQLite, full-text search, user-editable categories, safer Docker defaults, and verified backup-first upgrades.
Agent Skills
AI assistant for Obsidian with , , and powered by Google Gemini.
基于 Claude Code Agent Skills 的 AI 提示词工程系统 - 10个场景化专家，自动路由，精准生成优秀提示词 ## 项目简介 这是一个基于 Claude Code Agent Skills 技术的智能提示词生成系统。通过自然语言请求，系统会自动路由到对应的专业 Skill，帮助用户写出高质量的 AI 提示词。
基于 LangGraph 和 DeepAgents 框架的智能体 Skills 能力演示项目。
基于 GJB 438C-2021 [5.10] 标准模板的 SRS 文档自动生成
Generate and review MiniMax H3 video prompts from user goals and multimodal references.
面向 AI Agent 的精选 Skills 集合。每一个 skill 都在日常工作中实际使用、迭代、踩过坑，覆盖内容创作、设计视觉、工具集成、合规文书等场景。
Command-line tool for distributed LLM inference benchmarks on SLURM clusters using TensorRT LLM, SGLang and vLLM.
Ready-to-run training recipes for reinforcement learning (GRPO, DAPO, GSPO, CISPO), preference optimization (DPO, ORPO), and supervised fine-tuning (SFT) on Fireworks.
A git custom command that enhances Git's native worktree functionality with interactive features, automation, and repository migration capabilities.
先归根，再分化；先明道，再造物。 从混沌需求出发，生成可运行、可验证、可进化的 Agent Skill。
"Writing doesn't just communicate ideas; it generates them."